gsd-debug

Orchestrate sub-agent collaboration for persistent state debugging across context resets.

Updated May 3, 2026

Search Tags:#systematic debugging #issue resolution #persistent state #scientific method #subagent isolation

Ready to run

npx skills add https://github.com/ThiagoVitale/endless-crystal --skill gsd-debug-thiagovitale

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gsd-debug
Source: https://github.com/ThiagoVitale/endless-crystal/tree/main/.codex/skills/gsd-debug
Command: npx skills add https://github.com/ThiagoVitale/endless-crystal --skill gsd-debug-thiagovitale

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gsd-sdk, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

The gsd-debug Skill addresses the challenge of debugging complex issues with persistent state across context resets, providing a systematic approach for issue resolution.

Core Features & Use Cases

Persistent State Debugging: Maintain debug context across resets, allowing for a detailed and continuous investigation.
Scientific Method Application: Follows a structured debugging process, including hypothesis testing and evidence collection.
Subagent Isolation: Isolates sub-agents for focused investigation, preserving main context integrity.
Flags and Subcommands: Offers diagnostic capabilities with --diagnose flag and manages sessions with list, status, and continue subcommands.

Quick Start

Run the gsd-debug list command to see active debug sessions. Start a new session with gsd-debug <issue description>.

Frequently Asked Questions about gsd-debug

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I maintain debug context across context resets when investigating complex issues?▼

Persistent state debugging maintains your debug context across context resets, allowing for detailed and continuous investigation of complex issues without losing prior progress.

What's the best way to apply the scientific method to systematic debugging?▼

Systematic debugging applies the scientific method through a structured process of hypothesis testing and evidence collection, ensuring complex issues are resolved methodically rather than through trial and error.

How do I isolate sub-agents for focused investigation without losing main context integrity?▼

Subagent isolation separates focused investigation tasks into distinct sub-agents, preserving the main context integrity while enabling parallel or independent issue resolution workflows.

Do I need Claude Code to use persistent state debugging for issue resolution?▼

Yes, Claude Code is required to enable request_user_input and spawn_agent interactions, which are essential for orchestrating agent collaboration during persistent state debugging sessions.

How do I manage and resume active debug sessions using the command line?▼

Run the diagnostic command with `--diagnose` for capabilities, and use `list`, `status`, and `continue` subcommands to manage active debug sessions and resume persistent investigations.

Why does my systematic debugging workflow break down when resolving persistent state issues?▼

Complex issue resolution breaks down without persistent state management, but this skill orchestrates agent collaboration to maintain debug context and apply structured hypothesis testing across resets.